OBJECTIVE: To identify the acupoint combinations used in the treatment of Alzheimer's disease(AD).METHODS: The clinical literature regarding acupuncture and moxibustion for AD was searched and collected from datab...OBJECTIVE: To identify the acupoint combinations used in the treatment of Alzheimer's disease(AD).METHODS: The clinical literature regarding acupuncture and moxibustion for AD was searched and collected from databases including Chinese Biomedical Medicine, China National Knowledge Infrastructure, Wanfang Database and PubMed. The database of acupuncture and moxibustion prescriptions for AD was established by using Excel software so as to conduct the descriptive analysis, association analysis on the data.RESULTS: Baihui(GV 20), Sishencong(EX-HN 1),Shenmen(HT 7), Zusanli(ST 36), Neiguan(PC 6),Fengchi(GB 20), Taixi(KI 3), Dazhui(GV 14), Shenshu(BL 23), Sanyinjiao(SP 6), Shenting(GV 24), Fenglong(ST 40), Xuanzhong(GB 39), Shuigou(GV 26)and Taichong(LR 3) were of higher frequency in the treatment of AD with acupnucture and moxibustion. Most acupoints were selected from the Governor Vessel. The commonly used acupoints were located on the head, face, neck and lower limbs. The combination of the local acupoints with the distal ones was predominated. The crossing points among the specific points presented the advantage in the treatment. The association analysis indicated that the correlation among Fengchi(GB 20)-Baihui(GV 20) was the strongest, followed by combinations of Dazhui(GV 14)-Baihui(GV 20), Shenshu(BL 23)-Baihui(GV 20) and Neiguan(PC 6)-Baihui(GV 20) and indicated the common rules of the clinical acupoint selection and combination for AD.CONCLUSION: Our findings provide a reference for acupoints selection and combination for AD in clinical acupuncture practice.展开更多
As a kind of flexible three-dimensional geometric data, point clouds can accomplish many challenging tasks so long as the rich information in the geometric topology architecture can be deeply analyzed. On account of t...As a kind of flexible three-dimensional geometric data, point clouds can accomplish many challenging tasks so long as the rich information in the geometric topology architecture can be deeply analyzed. On account of that point cloud data is sparse, disordered and rotation-invariant, the success of convolutional neural network in 2 D image cannot be directly reproduced on point cloud. In this paper, we propose WECNN, namely, Weight-Edge Convolution Neural Network, which has an excellent ability to utilize local structural features. As the core of WECNN, a novel convolution operator called WEConv tries to capture structural features by constructing a fixed number of directed graphs and extracting the edge information of the graph to further analyze the local regions of point cloud. Moreover, a weight function is designed for different tasks to assign weights to the edges, so that feature extractions on the edges can be more fine-grained and robust. WECNN gets overall accuracy of 93.8% and mean class accuracy of 91.6% on Model Net40 dataset. At the same time, it gets a mean Io U of 85.5% on Shape Net Part dataset. Results of extensive experiments show that our WECNN outperforms other classification and segmentation approaches on challenging benchmarks.展开更多
基金Supported by National Natural Science Foundation of China(No.81373741)National Natural Science Foundation of China(No.81473786)Chinese Medicine and Integrated Medicine Research Projects[2017,No.20]Funded by Health and Family Planning Commission of Hubei Province(No.24)
文摘OBJECTIVE: To identify the acupoint combinations used in the treatment of Alzheimer's disease(AD).METHODS: The clinical literature regarding acupuncture and moxibustion for AD was searched and collected from databases including Chinese Biomedical Medicine, China National Knowledge Infrastructure, Wanfang Database and PubMed. The database of acupuncture and moxibustion prescriptions for AD was established by using Excel software so as to conduct the descriptive analysis, association analysis on the data.RESULTS: Baihui(GV 20), Sishencong(EX-HN 1),Shenmen(HT 7), Zusanli(ST 36), Neiguan(PC 6),Fengchi(GB 20), Taixi(KI 3), Dazhui(GV 14), Shenshu(BL 23), Sanyinjiao(SP 6), Shenting(GV 24), Fenglong(ST 40), Xuanzhong(GB 39), Shuigou(GV 26)and Taichong(LR 3) were of higher frequency in the treatment of AD with acupnucture and moxibustion. Most acupoints were selected from the Governor Vessel. The commonly used acupoints were located on the head, face, neck and lower limbs. The combination of the local acupoints with the distal ones was predominated. The crossing points among the specific points presented the advantage in the treatment. The association analysis indicated that the correlation among Fengchi(GB 20)-Baihui(GV 20) was the strongest, followed by combinations of Dazhui(GV 14)-Baihui(GV 20), Shenshu(BL 23)-Baihui(GV 20) and Neiguan(PC 6)-Baihui(GV 20) and indicated the common rules of the clinical acupoint selection and combination for AD.CONCLUSION: Our findings provide a reference for acupoints selection and combination for AD in clinical acupuncture practice.
基金Supported by the National Natural Science Foundation of China (61772328)。
文摘As a kind of flexible three-dimensional geometric data, point clouds can accomplish many challenging tasks so long as the rich information in the geometric topology architecture can be deeply analyzed. On account of that point cloud data is sparse, disordered and rotation-invariant, the success of convolutional neural network in 2 D image cannot be directly reproduced on point cloud. In this paper, we propose WECNN, namely, Weight-Edge Convolution Neural Network, which has an excellent ability to utilize local structural features. As the core of WECNN, a novel convolution operator called WEConv tries to capture structural features by constructing a fixed number of directed graphs and extracting the edge information of the graph to further analyze the local regions of point cloud. Moreover, a weight function is designed for different tasks to assign weights to the edges, so that feature extractions on the edges can be more fine-grained and robust. WECNN gets overall accuracy of 93.8% and mean class accuracy of 91.6% on Model Net40 dataset. At the same time, it gets a mean Io U of 85.5% on Shape Net Part dataset. Results of extensive experiments show that our WECNN outperforms other classification and segmentation approaches on challenging benchmarks.
